{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NC5JSEZ6COOO2KJRUDOUEBLKTT","short_pith_number":"pith:NC5JSEZ6","schema_version":"1.0","canonical_sha256":"68ba99133e139ced2931a0dd42056a9cd5f3d1c9f04d21a8ac68f0c746c292ae","source":{"kind":"arxiv","id":"1812.02035","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Model Pruning via Weight Dropping Away and Back","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changhao Sun, Da Fan, Haipeng Jia, Meiyu Huang, Xueshuang Xiang, Yang He","submitted_at":"2018-12-05T15:19:19Z","abstract_excerpt":"Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of progress in model compression, traditional gradual pruning approaches involve an iterative prune-retrain procedure and may suffer from two critical issues: local importance judgment, where the pruned weights are merely unimportant in the current model; and an irretrievable pruning process, where the pruned weights have no chance to come back. Addressing thes"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.02035","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T15:19:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a61d84550bd6f2673e692ee7fd4de9ec7b2b8143b6bc78f1b1cb047f12f45bb1","abstract_canon_sha256":"0748518ea44b965a00b57ad453ac7e375d1fbb6be4b67fa82b5d0cdccbdc8d8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:11.493107Z","signature_b64":"uOFFUPXQZPr1I9MSByNOjK5zYP1GsMPShtJynVkNC3cptCgRH9zqRuFgXp6706d2AVrZDGK5Da6oCG7E8xRJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ba99133e139ced2931a0dd42056a9cd5f3d1c9f04d21a8ac68f0c746c292ae","last_reissued_at":"2026-07-05T00:54:11.492613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:11.492613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Model Pruning via Weight Dropping Away and Back","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changhao Sun, Da Fan, Haipeng Jia, Meiyu Huang, Xueshuang Xiang, Yang He","submitted_at":"2018-12-05T15:19:19Z","abstract_excerpt":"Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of progress in model compression, traditional gradual pruning approaches involve an iterative prune-retrain procedure and may suffer from two critical issues: local importance judgment, where the pruned weights are merely unimportant in the current model; and an irretrievable pruning process, where the pruned weights have no chance to come back. Addressing thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02035","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1812.02035/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.02035","created_at":"2026-07-05T00:54:11.492676+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02035v2","created_at":"2026-07-05T00:54:11.492676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02035","created_at":"2026-07-05T00:54:11.492676+00:00"},{"alias_kind":"pith_short_12","alias_value":"NC5JSEZ6COOO","created_at":"2026-07-05T00:54:11.492676+00:00"},{"alias_kind":"pith_short_16","alias_value":"NC5JSEZ6COOO2KJR","created_at":"2026-07-05T00:54:11.492676+00:00"},{"alias_kind":"pith_short_8","alias_value":"NC5JSEZ6","created_at":"2026-07-05T00:54:11.492676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT","json":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT.json","graph_json":"https://pith.science/api/pith-number/NC5JSEZ6COOO2KJRUDOUEBLKTT/graph.json","events_json":"https://pith.science/api/pith-number/NC5JSEZ6COOO2KJRUDOUEBLKTT/events.json","paper":"https://pith.science/paper/NC5JSEZ6"},"agent_actions":{"view_html":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT","download_json":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT.json","view_paper":"https://pith.science/paper/NC5JSEZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02035&json=true","fetch_graph":"https://pith.science/api/pith-number/NC5JSEZ6COOO2KJRUDOUEBLKTT/graph.json","fetch_events":"https://pith.science/api/pith-number/NC5JSEZ6COOO2KJRUDOUEBLKTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT/action/storage_attestation","attest_author":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT/action/author_attestation","sign_citation":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT/action/citation_signature","submit_replication":"https://pith.science/pith/NC5JSEZ6COOO2KJRUDOUEBLKTT/action/replication_record"}},"created_at":"2026-07-05T00:54:11.492676+00:00","updated_at":"2026-07-05T00:54:11.492676+00:00"}